Hume AI, a startup focused on emotionally intelligent voice interfaces, has recently launched an experimental feature called "Voice Control."
This new tool aims to help developers and users create personalized AI voices without any coding, AI prompt engineering, or sound design skills. Users can easily customize voices that meet their needs by precisely adjusting voice characteristics.
This new feature builds on the company's previous release, "Empathic Voice Interface 2" (EVI2), which enhanced the naturalness, emotional responsiveness, and customizability of voices. Unlike traditional voice cloning technologies, Hume's products focus on providing unique and expressive voices to meet the needs of various applications, including customer service chatbots, digital assistants, teachers, tour guides, and accessibility features.
The Voice Control feature allows developers to adjust voice characteristics across ten different dimensions, including gender, assertiveness, excitement, and confidence.
“Male/Female: The voice's gender ranges from more masculine to more feminine.
Confidence: The firmness of the voice, ranging from timid to bold.
Buoyancy: The density of the voice, ranging from deflated to buoyant.
Assurance: The level of certainty in the voice, ranging from shy to confident.
Enthusiasm: The excitement in the voice, ranging from calm to enthusiastic.
Nasal Quality: The openness of the voice, ranging from clear to nasal.
Relaxation: The stress level in the voice, ranging from tense to relaxed.
Smoothness: The texture of the voice, ranging from smooth to staccato.
Gentleness: The vigor behind the voice, ranging from gentle to powerful.
Tightness: The inclusiveness of the voice, ranging from tight to breathy.”
Users can fine-tune these attributes in real-time using virtual sliders, making customization straightforward and clear. This feature is currently available on Hume's virtual platform, accessible to users who register for free.
Voice Control has been released in a testing version and is integrated with Hume's Empathic Voice Interface (EVI), making it suitable for a wide range of applications. Developers can choose a base voice, adjust its characteristics, and preview the results in real-time. This process ensures repeatability and stability between interactions, which are key features for real-time applications like customer service bots or virtual assistants.
The impact of EVI2 is evident in the Voice Control feature. Early models introduced functionalities such as conversational prompts and multilingual capabilities, broadening the scope of voice AI applications. For example, EVI2 supports sub-second response times for natural, instant conversations. It also allows for dynamic adjustments to speaking styles during interactions, making it a versatile tool for businesses.
This move addresses the issue of dependency on preset voices in the AI industry, where many brands or applications often struggle to find voices that meet their needs. Hume's goal is to develop emotionally nuanced voice AI to drive industry advancement. EVI2, released in September 2024, significantly improved voice latency and cost-effectiveness while providing a secure alternative for voice modulation.
Hume's research-driven approach plays a central role in product development, combining cross-cultural voice recordings and emotional survey data. This methodology forms the foundation of EVI2 and the newly launched Voice Control, enabling it to capture human perception of voice in great detail.
Currently, Voice Control is in testing and is combined with Hume's Empathic Voice Interface (EVI) to support various application scenarios. Developers can select a base voice, adjust its characteristics, and preview results in real-time, ensuring consistency and stability in real-time applications like customer service or virtual assistants.
As competition in the market intensifies, Hume's personalized voice and emotional intelligence positioning make it stand out in the voice AI field. In the future, Hume plans to expand the capabilities of Voice Control, adding adjustable dimensions, optimizing voice quality, and increasing the range of base voice options.
Official Blog: https://www.hume.ai/blog/introducing-voice-control
Key Points:
🔊 **Hume AI has launched the "Voice Control" feature, allowing users to easily create personalized AI voices.**
🛠️ **This feature requires no coding skills, and users can adjust voice characteristics using sliders.**
🌐 **Hume aims to meet diverse application needs with personalized and emotionally intelligent voice AI.**
